Error Training Naive Bayes Classifier

[amin (Amin Ferdous)]

Hi,
I am a beginner in Bio-informatic field using qiime/2.2019.04, while training a Naive Bayes classifier, I get following error:

Plugin error from feature-classifier:

Invalid characters in sequence: ['k', 'n', 'r', 's'].
Valid characters: ['K', 'S', 'G', 'T', '-', 'Y', 'N', 'R', 'V', 'A', '.', 'W', 'C', 'D', 'H', 'M', 'B']
Note: Use lowercase if your sequence contains lowercase characters not in the sequence's alphabet.

I checked my .fas file, It does not contain any lower case letter (It contained lower case letter earlier but I made them uppercase finally). I would be really grateful, if you are able to solve the problem. For your consideration I attached my .qza files.
Regards,
AminoutTACG_otus.qza (678.1 KB)
ref1-taxonomy.qza (128.0 KB)

[timanix (Timur Yergaliyev)]

Hi!
Just checked your dna-sequences.fasta, it still contains some lower case letters.

[amin (Amin Ferdous)]

Thanks a lot…I am checking again.